Hardware comparison
AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) vs NVIDIA RTX Pro 6000 Blackwell (96GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 69 tracked models each one can run.
Scroll sideways to compare both machines. Keyboard: focus the table, then use the arrow keys. Metric names stay visible.
| Hardware | AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | NVIDIA RTX Pro 6000 Blackwell (96GB) |
|---|---|---|
| Memory | 128.0 GB (better for this comparison) | 96.0 GB |
| Bandwidth | 256 GB/s | 1792 GB/s (better for this comparison) |
| Price (approx) | $2,999Complete system | $12,999GPU only · host PC required, sold separately |
| LLMs it runs | 62 of 69 | 62 of 69 |
| Best model it runs | Gemma 4 31BQ2_K · estimated 12–19 tok/s | Gemma 4 31BFP16 · estimated 20–30 tok/s |
These prices cover different purchases: a GPU card excludes its required host PC; a complete system includes the machine. No price winner is marked. Prices are approximate catalog estimates; check current configurations and prices before buying.
The recommended quants differ. These estimated speeds are not a like-for-like comparison. Estimates use 4,096 context tokens, llama.cpp and one stream.
Both run the same number of models, but the AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) has more memory (128.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX Pro 6000 Blackwell (96GB) has more memory bandwidth (1792 GB/s). Higher bandwidth can help generation speed, but model, quant, architecture and runtime also affect the estimates.